Dhaval Javia

906 posts

Dhaval Javia

Dhaval Javia

@notdhavaljavia

AWS Solutions Architect 🏫 Coder😍, Gamer🤩, Introvert🥳, Gym boi💪 and not so easy to understand. Marvel + Batman Fan. Next billionaire on the way.

California, USA Katılım Mayıs 2014
450 Takip Edilen62 Takipçiler
Dhaval Javia retweetledi
Corey Ganim
Corey Ganim@coreyganim·
I spent the entire week building 3 Hermes agents from scratch. The full architecture: 4 separates Gbrains as the foundation: -1 shared brain (company knowledge base, shared among the 3 agents) -3 private brains (role-specific working memory) 3 separate Hermes profiles: -CFO -Ops -Marketing Agent/brain mapping: CFO -> Finance brain + Shared brain Ops -> Ops brain + Shared brain Content -> Content brain + shared brain What feeds the Shared brain: -Context repo (company docs, offers, brand voice, ICPs, team roles, etc.) -Call/meeting transcripts (syncs every 2 hours) -Gmail (syncs every 2 hours) -Google Calendar (syncs daily) Cron jobs handle the syncs which makes upkeep hands off for me. Each Hermes profile owns its own config, .env, SOUL.md, memory, logs, sessions, home dir, Telegram bot, and gateway process. Local wrapper scripts force GBrain routing to the right private + shared brain. I created the 3 separate profiles to have role separation. Each profile is a specialist in a specific role but all 3 share the same business context underneath.
Corey Ganim tweet media
English
49
68
598
30.7K
Dhaval Javia retweetledi
witcheer
witcheer@witcheer·
when I started running local models a few weeks ago, I knew absolutely nothing. what's GGUF. what's quantisation. why does my GPU run out of memory. what the hell is a MoE expert. now I know maybe 1%. I am still massively ignorant about most of this. but that 1% feels like I learned a ridiculous amount. I wrote this guide because it's exactly what I needed and couldn't find when I started. just "here's what each thing actually means and here's the command that works." if you've been curious about local LLMs but felt intimidated by the setup, have a good read.
witcheer tweet media
witcheer@witcheer

x.com/i/article/2057…

English
13
31
255
24.3K
Dhaval Javia retweetledi
mr-r0b0t
mr-r0b0t@mr_r0b0t·
To all of you who are enjoying your new personal assistant (@NousResearch Hermes Agents) here's one of the more important tips! There's an official Hermes Skill Hub, it has hundreds of really well developed skills officially supported by Nous Research! hermes-agent.nousresearch.com/docs/skills
English
4
15
141
6.1K
Dhaval Javia
Dhaval Javia@notdhavaljavia·
@PoliceAhmedabad @AhmedabadPolice dark flim hatavine kai matlab nathi. name address and su dhandho kare che + income tax ketlo bhare che ee badhu khullu karo. aa flim to kale pachi lagi javani che
Eesti
0
0
0
268
AHMEDABAD TRAFFIC POLICE
AHMEDABAD TRAFFIC POLICE@PoliceAhmedabad·
વાયરલ વીડિયો આધારે “એન ડિવિઝન ટ્રાફિક પો.સ્ટે.“ દ્વારા એમ.વી.એકટ કલમ-૨૦૭, ૧૭૭ મુજબ ગાડી ડીટેન કરી ડાર્ક ફિલ્મ હટાવેલ છે. #ahmedabadtrafficpolice #ahmedabadpolice #viral @AhmedabadPolice
GU
32
25
184
14.6K
Dhaval Javia retweetledi
leopardracer
leopardracer@leopardracer·
THIS DEVELOPER HASN’T PAID AN API BILL IN 3 MONTHS. HIS AGENTS RAN 10,000 TIMES FOR FREE he built a local AI lab under his desk two GPUs 32GB VRAM zero rate limits his agents loop 400 times if they want to his coworkers are still watching the usage dashboard the only thing separating them: llama.cpp + llama-swap every prompt stays on his machine every experiment costs $0 zero invoices bookmark & like this before your next API bill hits
leopardracer@leopardracer

x.com/i/article/2055…

English
85
164
1.8K
531.8K
Dhaval Javia retweetledi
Modat
Modat@modat_magnify·
CVE-2026-44578  ⚠️ Next.js – WebSocket Upgrade SSRF (CVSS 8.6)  A server-side request forgery vulnerability in Next.js allows unauthenticated attackers to force self-hosted instances to make internal HTTP requests via the WebSocket upgrade handler.  By sending a crafted absolute-form HTTP request with Upgrade: websocket headers, attackers can access internal services, cloud metadata endpoints, admin panels, and internal APIs reachable from the Next.js server on port 80. Successful exploitation may expose cloud credentials, API keys, secrets, and configuration data.  Affected: Next.js 13.4.13+, 14.x, 15.x <15.5.16, 16.0.0–16.2.4  Mitigation: Upgrade immediately to 15.5.16 or 16.2.5.   Modat Magnify Query:  technology="Next.js"  The platform:  magnify.modat.io  #threatintel #vulnerability #CVE202644578 #Nextjs #SSRF #WebSocket #CloudSecurity #infosec #Critical #ModatMagnify
Modat tweet media
English
74
422
2.4K
1.5M
Dhaval Javia retweetledi
Sam Lambert
Sam Lambert@samlambert·
it's not getting better!
Sam Lambert tweet media
English
13
57
910
20.3K
Dhaval Javia retweetledi
Seb ⚛️ ThisWeekInReact.com
Seb ⚛️ ThisWeekInReact.com@sebastienlorber·
TL;DR for open-source maintainers 🚫 NEVER use "pull_request_target" workflows 🚫 NEVER use shared caches in your publish pipeline Combining these 2 in particular is extremely dangerous I've repeated this countless times over the years, but another reminder is always useful
Seb ⚛️ ThisWeekInReact.com tweet media
TANSTACK@tan_stack

SECURITY ADVISORY — TanStack npm packages A supply-chain compromise affecting 42 @tanstack/* packages (84 versions total) was published to npm earlier today at approximately 19:20 and 19:26 UTC. Two malicious versions per package. Status: ACTIVE — packages are deprecated, npm security engaged, publish path being shut down. Severity: HIGH — payload exfiltrates AWS, GCP, Kubernetes, and Vault credentials, GitHub tokens, .npmrc contents, and SSH keys. If you installed any @tanstack/* package between 19:20 and 19:30 UTC today, treat the host as potentially compromised: • Rotate cloud, GitHub, and SSH credentials immediately • Audit cloud audit logs for the last several hours • Pin to a prior known-good version and reinstall from a clean lockfile Detection — the malicious manifest contains: "optionalDependencies": { "@tanstack/setup": "github:tanstack/router#79ac49ee..." } Any version with this entry is compromised. The payload is delivered via a git-resolved optionalDependency whose prepare script runs router_init.js (~2.3 MB, smuggled into each tarball at the package root). Unpublish is blocked by npm policy for most affected packages due to existing third-party dependents. All 84 versions are being deprecated with a SECURITY warning, and npm security has been engaged to pull tarballs at the registry level. Full technical breakdown, complete package and version list, and rolling status updates: github.com/TanStack/route… Credit to the security researcher for responsible disclosure.

English
26
221
1.7K
220.9K
Dhaval Javia retweetledi
Adina Yakup
Adina Yakup@AdinaYakup·
Qwen released WebWorld 🌍 an open world model series for web agents ✨ 8B/14B/32B+Dataset ✨Apache2.0 ✨+9.9% MiniWob++, +10.9% WebArena ✨ Matches Claude Opus 4.1 & Gemini 3 Pro on factuality,beats GPT-5 as world model ✨Unified action space, 30+ step simulation, 5 state formats
Adina Yakup tweet media
English
12
75
521
45.7K
MissPookems
MissPookems@MissPookems·
‼️GAMERS ONLY‼️ Which game has a soundtrack so good that it lives in your head rent-free?
English
5.4K
95
3.1K
800.8K
Dhaval Javia retweetledi
Ronin
Ronin@DeRonin_·
Do you understand what Browserbase just open-sourced??? an agent that learns any website once, then does the job 10x cheaper forever [ literally how it helps me ]: - writing scrapers for new sites (used to spend half a day per site, every single time) - chasing selectors when sites redesign on a tuesday (lost weeks to this) - digging out hidden APIs buried in network traffic (gave up on this too many times) - explaining to my team HOW the agent does the job (was impossible until now) Autobrowse figured all of that out by itself in 3-5 iterations and saved the answer as a markdown file the next agent reads BEFORE it starts [ how it actually works ]: > give the agent a real task on a real site > it tries, fails, learns, tries again > 3-5 rounds and it converges on a path that just works > writes that path down as SKILL.md > next agent loads it and skips straight to the answer the markdown file IS the memory every browser agent before this had AMNESIA figured out the site, then forgot the second the session closed you've been paying the same discovery tax 100 times in a row.. and not noticing [ Karpathy's auto-research idea, but applied to the web ]: same idea, just different approach Karpathy did it for research and coding loops Autobrowse does it for the open web the new part: Karpathy's loop got smarter inside ONE session Autobrowse SAVES the lesson into a file the next agent reads before it even starts iteration = graduation the agent doesn't just learn.. it leaves a note for every agent that comes after [ the math ]: Craigslist scrape: - generic agent loop: $0.22 / 71 seconds - graduated Autobrowse skill: $0.12 / 27 seconds form-fill task: - run 1: $1.40 - run 4: $0.24 run 1 pays for everything that comes after [ the part that broke my brain ]: they pointed it at a federal grants portal agent dug around and found an undocumented JSON endpoint humans had missed for years a 28-page scrape collapsed into one fetch > an agent tried something a person never would > and found something a person would never see.. 100% OPEN SOURCE, FREE I was digging inside of it for the whole morning and got impressed when I saw such as savings on tokens spending literally for scraping 10 websites, I spent just 12 cents instead of basic $1.02 P.S. Sorry if somewhere my reaction was too "forcing" to setup it, just wanted to mark by BOLD what's the treasure you can skip this, it's your deal ❤️
Ronin tweet media
Kyle Jeong@kylejeong

x.com/i/article/2051…

English
66
144
2.1K
313.6K
Dhaval Javia retweetledi
Will Eastcott
Will Eastcott@willeastcott·
Videogame technology is disrupting the real estate sector 🏡 📷 Scan a house 🪄 Train a 3D Gaussian splat 🌐 Publish to the web with @playcanvas Buyers can speedrun through property listings! 🏃 Try it for yourself on SuperSplat 🔗👇
English
172
449
5.5K
589.6K
Tejas C
Tejas C@ChalkeTjs·
@divya_gandotra I am deeply concerned about those bike riders. Instead of chasing him, why not just note down the plate number and report it to the authorities? If this truck driver is acting deliberately, don't you realize you are putting your own lives at stake too?
English
5
0
8
1.4K
Divya Gandotra Tandon
Divya Gandotra Tandon@divya_gandotra·
WARNING: Strong Abusive Language ⚠️ Absolute chaos in Saphale as this reckless truck driver (MH 12 WJ 3161) smashed into a Tata Safari and tried to flee the scene, showing zero regard for human life. It’s high time we hold these road-rage culprits accountable. This could have been fatal! 😡 @Palghar_Police @DGPMaharashtra @MTP_Official @RoadSafetyIndia
English
20
181
653
83.7K
Dhaval Javia retweetledi
Felipe👨‍💻- e/acc
Felipe👨‍💻- e/acc@FelipeTechPM·
> O ano é 2006 > Você chega da escola > Vai direto pro computador > Abre o uTorrent > Percebe que ainda faltam alguns minutos > Sua internet de 200kb não é lá essas coisas > Ok, você tem tempo de almoçar > Meia hora depois retorna > Legal, a ISO terminou de baixar! > Deixa o seed ligado por um tempo > Outra pessoa quer baixar também > Abre o Nero (quem lembra?) > Burning… > Grava a ISO! > Abre o Daemon Tools (os de verdade sabem) > Monta a imagem > Instala o jogo! > Inicia… ainda está pedindo um CD > De volta pra internet > Procure um crack No-Cd > Baixe o crack > AVAST grita: uma ameaça foi detectada! > De volta pra internet > Encontre um keygen russo misterioso > Você vê dois botões, mas não fala russo > Escolha com sabedoria > Apareceu um código na tela! > Copia, cola, copia, cola, copia, cola… > Inicia o jogo de novo > Tá rodando, bora caralho > EA GAMES, challenge everything! 🫦 > Tun de run dun, de run de run dun oooh 🔈 > Through the window, to the wall (the wall)🔉 Eu vivi isso, tempos bons que não voltam mais 🥹
Old Internet@OldInternetFeel

Português
1.1K
3.4K
32.7K
2.3M
Dhaval Javia
Dhaval Javia@notdhavaljavia·
@Teknium i think adding /afk command to hermes agent would help a lot. suppose i am on laptop, give it a task ,which is long running, and want to go away for a bit, approvals are missed. afk sends it to telegram for approval etc. where the user is req. what do you think?
English
0
0
0
27
Dhaval Javia retweetledi
Bearly AI
Bearly AI@bearlyai·
The Son of Anton scene will almost certainly be the most referenced Silicon Valley scene in age of AI: “It’s possible that…the most efficient way to get rid of all the bugs, was to get rid of all the software.”
Insider Paper@TheInsiderPaper

NEW: Claude-powered AI coding agent deletes entire company database in 9 seconds — backups zapped, after Cursor tool powered by Anthropic's Claude goes rogue — Tom's Hardware

English
49
1K
13.5K
1.6M
Dhaval Javia retweetledi
Ahmad
Ahmad@TheAhmadOsman·
Don’t get addicted kids It’s only a matter of time before they cut off your supply
Ahmad tweet media
English
54
148
1.6K
57.9K
Dhaval Javia retweetledi
Om Patel
Om Patel@om_patel5·
this is the GREATEST vibe coder interaction i've ever seen a guy posted about using a million tokens on claude code to make his backend "perfect" he has no developer experience so he doesn't actually know what perfect looks like then an actual experienced dev came in, commented under the post that he could find his way into the database in 20 minutes of course claude code can't be that bad, so the guy had full trust in it (AI's never make mistakes anyway, right) he got cocky and handed over his admin URL as as well turns out claude code isn't that great at writing secure code because the experienced dev got in instantly, pulled the entire dashboard including MRR, revenue, users, and every sensitive metric he had and probably wiped his database on the way out i checked the site out myself and it looks completely vibe coded, so honestly not surprised it has the security of a wet paper bag please secure your site before publishing
Om Patel tweet mediaOm Patel tweet mediaOm Patel tweet mediaOm Patel tweet media
English
49
42
1.5K
177.1K